AdaRec: Adaptive Recommendation with LLMs via Narrative Profiling and Dual-Channel Reasoning
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915609772556288 |
|---|---|
| author | Wang, Meiyun Polpanumas, Charin |
| author_facet | Wang, Meiyun Polpanumas, Charin |
| contents | We propose AdaRec, a few-shot in-context learning framework that leverages large language models for an adaptive personalized recommendation. AdaRec introduces narrative profiling, transforming user-item interactions into natural language representations to enable unified task handling and enhance human readability. Centered on a bivariate reasoning paradigm, AdaRec employs a dual-channel architecture that integrates horizontal behavioral alignment, discovering peer-driven patterns, with vertical causal attribution, highlighting decisive factors behind user preferences. Unlike existing LLM-based approaches, AdaRec eliminates manual feature engineering through semantic representations and supports rapid cross-task adaptation with minimal supervision. Experiments on real ecommerce datasets demonstrate that AdaRec outperforms both machine learning models and LLM-based baselines by up to eight percent in few-shot settings. In zero-shot scenarios, it achieves up to a nineteen percent improvement over expert-crafted profiling, showing effectiveness for long-tail personalization with minimal interaction data. Furthermore, lightweight fine-tuning on synthetic data generated by AdaRec matches the performance of fully fine-tuned models, highlighting its efficiency and generalization across diverse tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_07166 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AdaRec: Adaptive Recommendation with LLMs via Narrative Profiling and Dual-Channel Reasoning Wang, Meiyun Polpanumas, Charin Computation and Language Artificial Intelligence Computational Engineering, Finance, and Science We propose AdaRec, a few-shot in-context learning framework that leverages large language models for an adaptive personalized recommendation. AdaRec introduces narrative profiling, transforming user-item interactions into natural language representations to enable unified task handling and enhance human readability. Centered on a bivariate reasoning paradigm, AdaRec employs a dual-channel architecture that integrates horizontal behavioral alignment, discovering peer-driven patterns, with vertical causal attribution, highlighting decisive factors behind user preferences. Unlike existing LLM-based approaches, AdaRec eliminates manual feature engineering through semantic representations and supports rapid cross-task adaptation with minimal supervision. Experiments on real ecommerce datasets demonstrate that AdaRec outperforms both machine learning models and LLM-based baselines by up to eight percent in few-shot settings. In zero-shot scenarios, it achieves up to a nineteen percent improvement over expert-crafted profiling, showing effectiveness for long-tail personalization with minimal interaction data. Furthermore, lightweight fine-tuning on synthetic data generated by AdaRec matches the performance of fully fine-tuned models, highlighting its efficiency and generalization across diverse tasks. |
| title | AdaRec: Adaptive Recommendation with LLMs via Narrative Profiling and Dual-Channel Reasoning |
| topic | Computation and Language Artificial Intelligence Computational Engineering, Finance, and Science |
| url | https://arxiv.org/abs/2511.07166 |